测试大模型在推理链被干扰时的表现，发现不同错误类型影响差异大。
Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
- 设计五类推理链干扰，系统评估13个模型表现
- 小模型对数学错误最敏感，大模型抗干扰能力更强
- 适合需要可靠推理的场景，如自动评分与安全应用
Chain-of-Thought（CoT）提示已成为激发大语言模型（LLMs）推理能力的基础方法，但其对中间推理步骤扰动的鲁棒性尚不明确。本文对5种结构化扰动类型（MathError、UnitConversion、Sycophancy、SkippedSteps、ExtraSteps）进行了全面实证评估，涵盖参数量相差三个数量级的13个模型，测试其在数学推理任务中面对推理链注入扰动时的表现。关键发现显示：小模型在MathError扰动下准确率下降50-60%，但随规模增大显著改善；UnitConversion在所有规模下均造成>5%的损失；ExtraSteps仅导致0-6%的轻微下降；Sycophancy和SkippedSteps引起约10%的损失，且随模型规模略有缓解。结果表明，模型规模虽可提升部分鲁棒性，但并非普适保护因素。研究为多阶段推理流水线部署提供依据，强调需进行任务定制化的鲁棒性评估与应对策略。代码与结果见https://github.com/Mystic-Slice/CoTPerturbation。
原文摘要 · Abstract (English)
Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the robustness of this approach to corruptions in intermediate reasoning steps remains poorly understood. This paper presents a comprehensive empirical evaluation of LLM robustness to a structured taxonomy of 5 CoT perturbation types: \textit{MathError, UnitConversion, Sycophancy, SkippedSteps,} and \textit{ExtraSteps}. We evaluate 13 models spanning three orders of magnitude in parameter count, testing their ability to complete mathematical reasoning tasks despite perturbations injected in the reasoning chain. Our key findings reveal heterogeneous vulnerability patterns: MathError perturbations produce the most severe degradation in small models (50-60\% accuracy loss) but show strong scaling benefits; UnitConversion remains challenging across all scales (>5\% loss even for midsized models); ExtraSteps incur minimal accuracy degradation (0-6\%) even for the smallest of models; Sycophancy and SkippedSteps produce modest effects ($\sim$10\% loss for small models) and slightly improve with scale. Scaling relationships show that model size serve as a protective factor against many perturbations but not always. These findings have direct implications for deploying LLMs in multi-stage reasoning pipelines and underscore the necessity of task-specific robustness assessments and mitigation strategies. The code and results are available at https://github.com/Mystic-Slice/CoTPerturbation
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。